© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38833
    Prev
    Next
    INDEX
    Explanations

    assembly attributes and build paths

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric tokens containing decimal points (floating-point literals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noté
    -0.95
     cristi
    -0.93
     abril
    -0.92
    नलिखित
    -0.91
    Ｓ
    -0.90
    日から
    -0.89
    tienne
    -0.88
     favorita
    -0.88
     content
    -0.88
    Ｒ
    -0.87
    POSITIVE LOGITS
     and
    1.05
    ţele
    1.02
     marchandises
    0.97
    längerung
    0.96
     meestal
    0.94
     visitó
    0.94
     proprietà
    0.94
     empuj
    0.93
     funzionalità
    0.92
    Kun
    0.90
    Activations Density 0.004%

    No Known Activations